paper-with-me

Papers

Understanding Video Transformers via Universal Concept Discovery

2024-01-19 · CVPR 2024 1 · Matthew Kowal, Achal Dave, Rares Ambrus, Adrien Gaidon, Konstantinos G. Derpanis, Pavel Tokmakov

This paper studies the problem of concept-based interpretability of transformer representations for videos. Concretely, we seek to explain the decision-making process of video transformers based on high-level, spatiotemporal concepts that are automatically discovered. Prior research on concept-based interpretability has concentrated solely on image-level tasks. Comparatively, video models deal with the added temporal dimension, increasing complexity and posing challenges in identifying dynamic concepts over time. In this work, we systematically address these challenges by introducing the first Video Transformer Concept Discovery (VTCD) algorithm. To this end, we propose an efficient approach for unsupervised identification of units of video transformer representations - concepts, and ranking their importance to the output of a model. The resulting concepts are highly interpretable, revealing spatio-temporal reasoning mechanisms and object-centric representations in unstructured video models. Performing this analysis jointly over a diverse set of supervised and self-supervised representations, we discover that some of these mechanism are universal in video transformers. Finally, we show that VTCD can be used for fine-grained action recognition and video object segmentation.

📄 PDF Abstract BibTeX arXiv:2401.10831

Code (0)

등록된 구현이 없습니다.

Tasks

Action RecognitionDecision MakingFine-grained Action RecognitionSemantic SegmentationVideo Object SegmentationVideo Semantic Segmentation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Attention 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Adam 설명 없음
Residual Connection 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

HuMoCon: Concept Discovery for Human Motion Understanding

2025-01-01 · CVPR 2025 1 · Qihang Fang, Chengcheng Tang, Bugra Tekin, Shugao Ma 외

We present HuMoCon, a novel motion-video understanding framework designed for advanced human behavior analysis. The core of our method is a human motion concept discovery framework that efficiently trains multi-modal…

Video Understanding

Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers

2026-03-03 · Youngjun Jun, Seil Kang, Woojung Han, Seong Jae Hwang arxiv

Video Diffusion Transformers (DiTs) have been synthesizing high-quality video with high fidelity from given text descriptions involving motion. However, understanding how Video DiTs convert motion words into video remain…

Video Semantic Segmentation

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

2024-12-09 · Johanna Vielhaben, Dilyara Bareeva, Jim Berend, Wojciech Samek 외

Vision transformers (ViTs) can be trained using various learning paradigms, from fully supervised to self-supervised. Diverse training protocols often result in significantly different feature spaces, which are usually c…

Universal Approximation Theorem for a Single-Layer Transformer

2025-07-11 · Esmail Gumaan arxiv

Deep learning employs multi-layer neural networks trained via the backpropagation algorithm. This approach has achieved success across many domains and relies on adaptive gradient methods such as the Adam optimizer. Sequ…

Memory Consolidation Enables Long-Context Video Understanding

2024-02-08 · Ivana Balažević, Yuge Shi, Pinelopi Papalampidi, Rahma Chaabouni 외

Most transformer-based video encoders are limited to short temporal contexts due to their quadratic complexity. While various attempts have been made to extend this context, this has often come at the cost of both concep…

EgoSchemaVideo Understanding